检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Fu, Weiping Wei, Bifan Hu, Jianxiang Cai, Zhongmin Liu, Jun School of Computer Science and Technology Xi'an Jiaotong University Xi'an China School of Continuing Education Xi'an Jiaotong University Xi'an China MOE KLINNS Lab School of Automation Science and Engineering Xi'an Jiaotong University Xi'an China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an China

ISBN: (纸本)9798891761643

Automatically generated questions often suffer from problems such as unclear expression or factual inaccuracies, requiring a reliable and comprehensive evaluation of their quality. Human evaluation is widely used in the field of question generation (QG) and serves as the gold standard for automatic metrics. However, there is a lack of unified human evaluation criteria, which hampers consistent and reliable evaluations of both QG models and automatic metrics. To address this, we propose QGEval, a multi-dimensional Evaluation benchmark for Question Generation, which evaluates both generated questions and existing automatic metrics across 7 dimensions: fluency, clarity, conciseness, relevance, consistency, answerability, and answer consistency. We demonstrate the appropriateness of these dimensions by examining their correlations and distinctions. Through consistent evaluations of QG models and automatic metrics with QGEval, we find that 1) most QG models perform unsatisfactorily in terms of answerability and answer consistency, and 2) existing metrics fail to align well with human judgments when evaluating generated questions across the 7 dimensions. We expect this work to foster the development of both QG technologies and their evaluation. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A Symbolic Rule Integration Framework with Logic Transformer for Inductive Relation Prediction 24

A Symbolic Rule Integration Framework with Logic Transformer...

引用

33rd ACM Web Conference, WWW 2024

作者： Pan, Yudai Liu, Jun Zhao, Tianzhe Zhang, Lingling Lin, Yun Dong, Jin Song School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Xi'an China National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Shaanxi Xi'an China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi'an China Shanghai Jiao Tong University Shanghai China National University of Singapore Singapore Singapore

ISBN: (纸本)9798400701719

Relation prediction in knowledge graphs (KGs) aims at predicting missing relations in incomplete triples, whereas the dominant paradigm by KG embeddings has a limitation to predict the relation between unseen entities. This situation is called an inductive setting, which is more common in the real-world scenario. To handle this issue, implicit symbolic rules have shown great potential in capturing the inductive capability. However, it is still challenging to obtain precise representations of logic rules from KGs. The argument variability and predicate non-commutativity in symbolic rule integration make the modeling of component symbols difficult. To this end, we propose a novel inductive relation prediction model named SymRITa with a logic transformer integrating rules. SymRITa firstly extracts the subgraph, whose embeddings are captured by a graph network. Meanwhile, symbolic rule graphs in the subgraph can be generated. Then, the symbolic rules are modeled by a proposed logic transformer. Specifically, the input format based on the subgraph-based embeddings is to focus on the argument variability in symbolic rules. In addition, a conjunction attention mechanism in the logic transformer can resolve predicate non-commutativity in the symbolic rule integration process. Finally, the subgraph-based and symbol-based embeddings obtained from the previous steps are combined for the training regime, and prediction results as well as rules explaining the reasoning process are explicitly output. Extensive experiments on twelve inductive datasets show that SymRITa achieves outstanding effectiveness compared to state-of-the-art inductive baselines. Moreover, the logic rules with corresponding confidences provide an interpretable paradigm. © 2024 ACM.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Brief Survey of Distribution Robust Graph Neural Networks 11

A Brief Survey of Distribution Robust Graph Neural Networks

引用

11th International Conference on Information technology and Quantitative management, ITQM 2024

作者： Zheng, Lei Quan, Pei Shi, Yong Niu, Lingfeng The School of Mathematical Sciences University of Chinese Academy of Sciences Beijing100190 China The College of Economics and Management Beijing University of Technology Beijing100124 China The School of Economics and Management University of Chinese Academy of Sciences Beijing1001090 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China

Graph neural network is a powerful tool for solving various graph tasks, such as node classification and graph classification. However, there is increasing evidence suggesting that it is sensitive to distribution shifts and its performance is reduced by at least 10% when distribution shifts happen. In the last three years, to solve the wide existing distribution shifts, some distribution robust strategies have been designed specifically for graph neural networks. It is also one of the popular research topics in graph neural networks in recent years. Therefore, in this paper, we divide these strategies into three categories depending on the specific problems they solve: distribution shift for semi-supervised node classification, distribution shift for unsupervised node classification, and out-of-distribution shift for graph classification. Furthermore, we discuss and summarize the strategies for each type of problem. After investigating these strategies, we put forward future development direction. © 2024 The Authors.

关键词： Distribution generalization Graph neural networks Shift robust

来源：评论

学校读者我要写书评

暂无评论

Neighborhood collaborative classifiers

Neighborhood collaborative classifiers

引用

2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016

作者： Xu, Suping Yang, Xibei Tsang, Eric C. C. Mantey, Eric A. School of Computer Science and Engineering Jiangsu University of Science and Technology Zhenjiang212003 China School of Economics and Management Nanjing University of Science and Technology Nanjing210094 China Faculty of Information Technology Macau University of Science and Technology C-Macau519020 China Intelligent Information Processing Key Laboratory of Shanxi Province Shanxi University Taiyuan030006 China Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province Zhejiang Ocean University Zhoushan316022 China

ISBN: (纸本)9781509003891

In neighborhood rough set model, the majority rule based neighborhood classifier (NC) is easy to be misjudged with the increasing of the size of information granules. To remedy this deficiency, we propose a neighborhood collaborative classifier (NCC) based on the idea of collaborative representation based classification (CRC). NCC first performs feature selection with neighborhood rough set, and then instead of solving the classification problem by the majority rule, NCC solves a similar problem with collaborative representation among the neighbors of each unseen sample. Experiments on UCI data sets demonstrate that: 1) Our NCC achieves satisfactory performance in larger neighborhood information granules when compared with NC;2) NCC reduces the size of dictionary when compared with CRC. © 2016 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Reverse Perspective Network for Perspective-Aware Object Counting

Reverse Perspective Network for Perspective-Aware Object Cou...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yifan Yang Guorong Li Zhe Wu Li Su Qingming Huang Nicu Sebe School of Computer Science and Technology UCAS Beijing China Key Lab of Big Data Mining and Knowledge Management UCAS Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China University of Trento Trento Italy

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

One of the critical challenges of object counting is the dramatic scale variations, which is introduced by arbitrary perspectives. We propose a reverse perspective network to solve the scale variations of input images, instead of generating perspective maps to smooth final outputs. The reverse perspective network explicitly evaluates the perspective distortions, and efficiently corrects the distortions by uniformly warping the input images. Then the proposed network delivers images with similar instance scales to the regressor. Thus the regression network doesn't need multi-scale receptive fields to match the various scales. Besides, to further solve the scale problem of more congested areas, we enhance the corresponding regions of ground-truth with the evaluation errors. Then we force the regressor to learn from the augmented ground-truth via an adversarial process. Furthermore, to verify the proposed model, we collected a vehicle counting dataset based on Unmanned Aerial Vehicles (UAVs). The proposed dataset has fierce scale variations. Extensive experimental results on four benchmark datasets show the improvements of our method against the state-of-the-arts.

关键词： Distortion Training Feature extraction Estimation Convolution Kernel Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Overview of Essential Components in deep learning reference-based super resolution methods 11

Overview of Essential Components in deep learning reference-...

引用

11th International Conference on Information technology and Quantitative management, ITQM 2024

作者： Xue, Jiayu Liu, Junjie Shi, Yong School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China Sino-Danish College University of Chinese Academy of Sciences Beijing100049 China College of Information Science and Technology University of Nebraska at Omaha OmahaNE68182 United States

Reference-based super resolution (RefSR) aims to recover the lost details in a low-resolution image and generate a high-resolution result, guided by a high-resolution reference image with similar contents or textures. In contrast to the traditional single-image super-resolution, which focuses on the intrinsic properties of the single low-resolution image, the challenge of RefSR lies in matching and aggregating highly-related but misaligned reference images with low-resolution images. Several effective but complex designs have been proposed to address this challenge, which poses difficulties in implementing RefSR in real-world applications. In order to better understand the working mechanism of RefSR and design a more efficient and lightweight architecture, we provide a review about the essential components of the existing deep learning-based RefSR. We decompose and classify the common pipeline into four submodules according to the functionalities. Then, we summarize and describe the implementation details of the commonly-adopted approaches in each submodule. Finally, we discuss the challenges and promising research directions. © 2024 The Authors.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Comments on Yu et al’s Shared data Integrity Verification Protocol 4th

Comments on Yu et al’s Shared Data Integrity Verification P...

引用

4th Euro-China Conference on Intelligent data Analysis and Applications, ECC 2017

作者： Wu, Tsu-Yang Lin, Yueshan Wang, King-Hang Chen, Chien-Ming Pan, Jeng-Shyang Fujian Provincial Key Lab of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China National Demonstration Center for Experimental Electronic Information and Electrical Technology Education Fujian University of Technology Fuzhou350118 China School of Computer Science and Technology Harbin Institute of Technology - Shenzhen Shenzhen518055 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong

ISBN: (纸本)9783319685267

Recently, Yu et al. proposed a secure shared data integrity verification protocol called SDVIP 2 to ensure the integrity of outsourced file in the cloud. Unfortunately, we exploit the vulnerability of their protocol in this paper. We demonstrate an active adversary can modify the outsourced file such that the auditor is unable to detect in the auditing process. At the end of this paper, we also provide two suggestions to fix the proposed attack. © 2018, Springer International Publishing AG.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

Multi-view Feature Augmentation with Adaptive Class Activation Mapping

arXiv

引用

arXiv 2022年

作者： Gao, Xiang Tian, Yingjie Qi, Zhiquan School of Computer Science and Technology University of Chinese Academy of Sciences China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences China

We propose an end-to-end-trainable feature augmentation module built for image classification that extracts and exploits multi-view local features to boost model performance. Different from using global average pooling (GAP) to extract vectorized features from only the global view, we propose to sample and ensemble diverse multi-view local features to improve model robustness. To sample class-representative local features, we incorporate a simple auxiliary classifier head (comprising only one 1×1 convolutional layer) which efficiently and adaptively attends to class-discriminative local regions of feature maps via our proposed AdaCAM (Adaptive Class Activation Mapping). Extensive experiments demonstrate consistent and noticeable performance gains achieved by our multi-view feature augmentation module. Copyright © 2022, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based embedding framework for object detection and recognition in underwater marine organisms

Research Square

引用

Research Square 2021年

作者： Zhu, Jinde Fujian Provincial Key Lab of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China

The detection of marine organisms is an important part of the intelligent strategy in marine ranch, which requires an underwater robot to detect the marine organism quickly and accurately in the complex ocean environment. Based on the latest deep learning arithmetic, this paper put forward to find the marine organism in a picture or video to construct a real-time objective invention system for marine organisms. The neural network arithmetic： YOLOv4 was employed to extract the deep features of marine organisms, implementing the accurate detection and size detection of different fish can use arithmetic for evaluation in fisheries. Furthermore, improving the architecture of the backbone and the neck connection is called YOLOv4-embedding. As a result, compared with other object detection arithmetic, YOLOv4-embedding object detection arithmetic was better at detection accuracy-higher detection confidence and higher detection ratio than other one-stage object detection arithmetic, EfficientDet-D3 example. The consequence demonstrates that the suggested instrument could implement the rapid invention of different varieties in marine organisms. Compared to the YOLOv4, the mAP75 of the YOLOv4-embedding achieves an improvement of 2.92% for the marine organism dataset at a rapid rate of ~51 FPS on RTX 3090, 60.8% AP50 for the MS COCO dataset. © 2021, CC BY.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

On-Line System of Garbage Image-Orientated Intelligent Classification, Submission and Examination

On-Line System of Garbage Image-Orientated Intelligent Class...

引用

IEEE International Conference on e-Business Engineering (ICEBE)

作者： Jiayin Tian Yaozhi Wang Jiaxin Liu Yan Chen School of Computer Science and Technology Xi'an Jiaotong University Xi'an Shaanxi China Shaanxi Key Lab of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an Shaanxi China Shaanxi Key Lab of Big Data Knowledge Engineering School of Computer Science and Technology Xi'an Jiaotong University Xi'an Jiaotong University Xi'an Shaanxi China

ISBN: (数字)9798350365856

ISBN: (纸本)9798350365863

In a world brimming with new products continually, novel waste types are ubiquitous. This makes current image-based garbage classification systems difficult to perform well due to the long-tailed effects of distribution of garbage types, and necessitates an urgent and efficient garbage classification with abilities of detecting new and rare wastes and class-incremental learning for environmental sustainability. Therefore, we propose a framework of Online System of Garbage Image-Oriented Intelligent Classification, Submission, and Examination, facilitating the incremental garbage classification efforts. In which, to identify novel garbage effectively, we also introduced few-shot object detection method with two key algorithms: Two-Stage Object Detection Learning Algorithm and Dynamic Query-based Incremental Few-shot Learning Algorithm. Our experiment results show that Both outperform the current existing ones in dataset, MS COCO. Then, a strategy of Class-Incremental learning based Residual Network is proposed to meet the need of new waste class-incremental learning. The experimental results support our strategy. Finally, a prototype system employed the above algorithms and the strategy is described.

关键词： Image recognition Heavily-tailed distribution Heuristic algorithms Green products Prototypes Object detection Classification algorithms Object recognition Few shot learning Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：